arXiv subjects

Masaki Hamada

Publications and source records attributed to Masaki Hamada.

3 recordsLinked to original sources

arXiv2022

Polyphone disambiguation and accent prediction using pre-trained language models in Japanese TTS front-end

Although end-to-end text-to-speech (TTS) models can generate natural speech, challenges still remain when it comes to estimating sentence-level phonetic and prosodic information from raw text in Japanese TTS systems. In this paper, we propose a method for polyphone disambiguation (PD) and accent prediction (AP). The proposed method incorporates explicit features extracted from morphological analysis and implicit features extracted from pre-trained language models (PLMs). We use BERT and Flair embeddings as implicit features and examine how to combine them with explicit features. Our objective evaluation results showed that the proposed method improved the accuracy by 5.7 points in PD and 6.0 points in AP. Moreover, the perceptual listening test results confirmed that a TTS system employing our proposed model as a front-end achieved a mean opinion score close to that of synthesized speech with ground-truth pronunciation and accent in terms of naturalness.

eess.AS↗

arXiv2020

Computing the nc-rank via discrete convex optimization on CAT(0) spaces

In this paper, we address the noncommutative rank (nc-rank) computation of a linear symbolic matrix \[ A = A_1 x_1 + A_2 x_2 + \cdots + A_m x_m, \] where each $A_i$ is an $n \times n$ matrix over a field $\mathbb{K}$, and $x_i$ $(i=1,2,\ldots,m)$ are noncommutative variables. For this problem, polynomial time algorithms were given by Garg, Gurvits, Oliveira, and Wigderson for $\mathbb{K} = \mathbb{Q}$, and by Ivanyos, Qiao, and Subrahmanyam for an arbitrary field $\mathbb{K}$. We present a significantly different polynomial time algorithm that works on an arbitrary field $\mathbb{K}$. Our algorithm is based on a combination of submodular optimization on modular lattices and convex optimization on CAT(0) spaces.

math.OC↗

arXiv2017

Maximum vanishing subspace problem, CAT(0)-space relaxation, and block-triangularization of partitioned matrix

In this paper, we address the following algebraic generalization of the bipartite stable set problem. We are given a block-structured matrix (partitioned matrix) $A = (A_{αβ})$, where $A_{αβ}$ is an $m_α$ by $n_β$ matrix over field ${\bf F}$ for $α=1,2,\ldots,μ$ and $β= 1,2,\ldots,ν$. The maximum vanishing subspace problem (MVSP) is to maximize $\sum_α \dim X_α + \sum_β \dim Y_β$ over vector subspaces $X_α \subseteq {\bf F}^{m_α}$ for $α=1,2,\ldots,μ$ and $Y_β \subseteq {\bf F}^{n_β}$ for $β= 1,2,\ldots,ν$ such that each $A_{αβ}$ vanishes on $X_α \times Y_β$ when $A_{αβ}$ is viewed as a bilinear form ${\bf F}^{m_α} \times {\bf F}^{n_β} \to {\bf F}$. This problem arises from a study of a canonical block-triangular form of $A$ by Ito, Iwata, and Murota~(1994), and is closely related to the noncommutative rank of a matrix with indeterminates. We prove that a weighted version (WMVP) of MVSP can be solved in psuedo polynomial time, provided arithmetic operations on ${\bf F}$ can be done in constant time. Our proof is a novel combination of submodular optimization on modular lattice and convex optimization on CAT(0)-space. We present implications of this result on block-triangularization of partitioned matrix.

math.OC↗